Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+
+---
+tags:
+- autotrain
+- text-regression
+base_model: distilbert/distilbert-base-uncased
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Regression
+
+## Validation Metrics
+loss: 0.02739923633635044
+
+mse: 0.02739923633635044
+
+mae: 0.10979370772838593
+
+r2: 0.008571624755859375
+
+rmse: 0.1655271468259827
+
+explained_variance: 0.020441055297851562

checkpoint-76/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "_num_labels": 1,
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "target"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "target": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "regression",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "vocab_size": 30522
+}

checkpoint-76/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0d2e4c01f155a5450cc49916c41293c1a12ba56a436b914d0beca432831ce28
+size 267829484

checkpoint-76/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c71fcaae1809658230e417caaf35ad1d4881dd8e8cc474b7329251de9c10a39a
+size 535718266

checkpoint-76/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc17a6051e9b5f0acb0f35b4fb75a05f870d06a0251a12c147ab76af0d27cc02
+size 13990

checkpoint-76/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9193ff89692fbba4cf254195b04cde91912398e77c179f71c638f3dddee3854e
+size 1064

checkpoint-76/trainer_state.json

@@ -0,0 +1,230 @@
+{
+  "best_metric": 0.02739923633635044,
+  "best_model_checkpoint": "autotrain-bert-arg/checkpoint-76",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 76,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": 2.780918598175049,
+      "learning_rate": 6.521739130434783e-06,
+      "loss": 0.0448,
+      "step": 3
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 0.544288158416748,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 0.062,
+      "step": 6
+    },
+    {
+      "epoch": 0.11842105263157894,
+      "grad_norm": 0.5275054574012756,
+      "learning_rate": 1.956521739130435e-05,
+      "loss": 0.0228,
+      "step": 9
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 0.8615014553070068,
+      "learning_rate": 2.608695652173913e-05,
+      "loss": 0.0381,
+      "step": 12
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 1.1464006900787354,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 0.0329,
+      "step": 15
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 0.22914494574069977,
+      "learning_rate": 3.91304347826087e-05,
+      "loss": 0.0148,
+      "step": 18
+    },
+    {
+      "epoch": 0.27631578947368424,
+      "grad_norm": 1.2268567085266113,
+      "learning_rate": 4.565217391304348e-05,
+      "loss": 0.05,
+      "step": 21
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.9654967188835144,
+      "learning_rate": 4.975609756097561e-05,
+      "loss": 0.0551,
+      "step": 24
+    },
+    {
+      "epoch": 0.35526315789473684,
+      "grad_norm": 0.9826757907867432,
+      "learning_rate": 4.902439024390244e-05,
+      "loss": 0.0466,
+      "step": 27
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 1.1838877201080322,
+      "learning_rate": 4.829268292682927e-05,
+      "loss": 0.0507,
+      "step": 30
+    },
+    {
+      "epoch": 0.4342105263157895,
+      "grad_norm": 0.40032073855400085,
+      "learning_rate": 4.75609756097561e-05,
+      "loss": 0.05,
+      "step": 33
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.7170906662940979,
+      "learning_rate": 4.682926829268293e-05,
+      "loss": 0.0338,
+      "step": 36
+    },
+    {
+      "epoch": 0.5131578947368421,
+      "grad_norm": 0.31745052337646484,
+      "learning_rate": 4.609756097560976e-05,
+      "loss": 0.0167,
+      "step": 39
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.7707906365394592,
+      "learning_rate": 4.536585365853659e-05,
+      "loss": 0.02,
+      "step": 42
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 0.7838310599327087,
+      "learning_rate": 4.4634146341463416e-05,
+      "loss": 0.0212,
+      "step": 45
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 1.0543047189712524,
+      "learning_rate": 4.390243902439025e-05,
+      "loss": 0.0372,
+      "step": 48
+    },
+    {
+      "epoch": 0.6710526315789473,
+      "grad_norm": 0.4342570900917053,
+      "learning_rate": 4.317073170731707e-05,
+      "loss": 0.0257,
+      "step": 51
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.37514448165893555,
+      "learning_rate": 4.2439024390243905e-05,
+      "loss": 0.0198,
+      "step": 54
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.3972807824611664,
+      "learning_rate": 4.170731707317073e-05,
+      "loss": 0.0234,
+      "step": 57
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.5491408705711365,
+      "learning_rate": 4.097560975609756e-05,
+      "loss": 0.0671,
+      "step": 60
+    },
+    {
+      "epoch": 0.8289473684210527,
+      "grad_norm": 0.46997275948524475,
+      "learning_rate": 4.0243902439024395e-05,
+      "loss": 0.0457,
+      "step": 63
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.7849195599555969,
+      "learning_rate": 3.951219512195122e-05,
+      "loss": 0.0409,
+      "step": 66
+    },
+    {
+      "epoch": 0.9078947368421053,
+      "grad_norm": 0.7742244005203247,
+      "learning_rate": 3.878048780487805e-05,
+      "loss": 0.0606,
+      "step": 69
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.23496082425117493,
+      "learning_rate": 3.804878048780488e-05,
+      "loss": 0.0279,
+      "step": 72
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 0.45524537563323975,
+      "learning_rate": 3.731707317073171e-05,
+      "loss": 0.0181,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "eval_explained_variance": 0.020441055297851562,
+      "eval_loss": 0.02739923633635044,
+      "eval_mae": 0.10979370772838593,
+      "eval_mse": 0.02739923633635044,
+      "eval_r2": 0.008571624755859375,
+      "eval_rmse": 0.1655271468259827,
+      "eval_runtime": 11.5516,
+      "eval_samples_per_second": 13.072,
+      "eval_steps_per_second": 0.866,
+      "step": 76
+    }
+  ],
+  "logging_steps": 3,
+  "max_steps": 228,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 20002220479488.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-76/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d216198309fb6f9912636e9dd495f35f3880a6122867d7ede41d12c540bd4b
+size 5368

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "_num_labels": 1,
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "target"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "target": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "regression",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0d2e4c01f155a5450cc49916c41293c1a12ba56a436b914d0beca432831ce28
+size 267829484

runs/Jul13_15-49-14_r-sebsa-asai-newstextbert-r5u4m245-e6f67-mmh1x/events.out.tfevents.1752421756.r-sebsa-asai-newstextbert-r5u4m245-e6f67-mmh1x.109.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c9ae7967377838e0ea15e0c1839f86b2b86886ead99fe8d7e64967d91770946
-size 5064
+oid sha256:ee19744418d8b178af2594531b7595dbb37cc0f18f00f5c065f2b97abed144e1
+size 22839

runs/Jul13_15-49-14_r-sebsa-asai-newstextbert-r5u4m245-e6f67-mmh1x/events.out.tfevents.1752422343.r-sebsa-asai-newstextbert-r5u4m245-e6f67-mmh1x.109.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb7feb9ef892653907fcae22ef06b577d4e6e56897aafade45368175104dc884
+size 609

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d216198309fb6f9912636e9dd495f35f3880a6122867d7ede41d12c540bd4b
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-bert-arg/autotrain-data",
+    "model": "distilbert/distilbert-base-uncased",
+    "lr": 5e-05,
+    "epochs": 3,
+    "max_seq_length": 128,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "text_column": "autotrain_text",
+    "target_column": "autotrain_label",
+    "logging_steps": -1,
+    "project_name": "autotrain-bert-arg",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "Sebsa",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}